From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dave Chinner Subject: [PATCH 6/6] xfs: add initial DAX support Date: Wed, 4 Mar 2015 10:30:27 +1100 Message-ID: <1425425427-16283-7-git-send-email-david@fromorbit.com> References: <1425425427-16283-1-git-send-email-david@fromorbit.com> Cc: linux-fsdevel@vger.kernel.org, jack@suse.cz, willy@linux.intel.com To: xfs@oss.sgi.com Return-path: Received: from ipmail06.adl6.internode.on.net ([150.101.137.145]:43321 "EHLO ipmail06.adl6.internode.on.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757807AbbCCXbQ (ORCPT ); Tue, 3 Mar 2015 18:31:16 -0500 In-Reply-To: <1425425427-16283-1-git-send-email-david@fromorbit.com> Sender: linux-fsdevel-owner@vger.kernel.org List-ID: From: Dave Chinner Add initial DAX support to XFS. To do this we need a new mount option to turn DAX on filesystem, and we need to propagate thi into the inode flags whenever an inode is instantiated so that the per-inode checks throughout the code Do The Right Thing. There are still some things remaining to be done: - needs per-inode flags to mark inodes as DAX enabled, and an inheritance flag to enable automatic filesystem propagation of the property - fails occasionally with zero length writes instead of ENOSPC errors, so error propagation inside/from the DAX code need work - occasionally creates two extents rather than a single larger extent like non-dax filesystems. - much more testing Signed-off-by: Dave Chinner --- fs/xfs/xfs_iops.c | 24 ++++++++++++------------ fs/xfs/xfs_mount.h | 2 ++ fs/xfs/xfs_super.c | 25 +++++++++++++++++++++++-- 3 files changed, 37 insertions(+), 14 deletions(-) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 3ff24c3..887d196 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1195,22 +1195,22 @@ xfs_diflags_to_iflags( struct inode *inode, struct xfs_inode *ip) { - if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE) + uint16_t flags = ip->i_d.di_flags; + + inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC | + S_NOATIME | S_DAX); + + if (flags & XFS_DIFLAG_IMMUTABLE) inode->i_flags |= S_IMMUTABLE; - else - inode->i_flags &= ~S_IMMUTABLE; - if (ip->i_d.di_flags & XFS_DIFLAG_APPEND) + if (flags & XFS_DIFLAG_APPEND) inode->i_flags |= S_APPEND; - else - inode->i_flags &= ~S_APPEND; - if (ip->i_d.di_flags & XFS_DIFLAG_SYNC) + if (flags & XFS_DIFLAG_SYNC) inode->i_flags |= S_SYNC; - else - inode->i_flags &= ~S_SYNC; - if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME) + if (flags & XFS_DIFLAG_NOATIME) inode->i_flags |= S_NOATIME; - else - inode->i_flags &= ~S_NOATIME; + /* XXX: Also needs an on-disk per inode flag! */ + if (ip->i_mount->m_flags & XFS_MOUNT_DAX) + inode->i_flags |= S_DAX; } /* diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 8c995a2..cd44e88 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -179,6 +179,8 @@ typedef struct xfs_mount { allocator */ #define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */ +#define XFS_MOUNT_DAX (1ULL << 62) /* TEST ONLY! */ + /* * Default minimum read and write sizes. diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 3ad0b17..0f26d7a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -112,6 +112,8 @@ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #define MNTOPT_DISCARD "discard" /* Discard unused blocks */ #define MNTOPT_NODISCARD "nodiscard" /* Do not discard unused blocks */ +#define MNTOPT_DAX "dax" /* Enable direct access to bdev pages */ + /* * Table driven mount option parser. * @@ -363,6 +365,10 @@ xfs_parseargs( mp->m_flags |= XFS_MOUNT_DISCARD; } else if (!strcmp(this_char, MNTOPT_NODISCARD)) { mp->m_flags &= ~XFS_MOUNT_DISCARD; +#ifdef CONFIG_FS_DAX + } else if (!strcmp(this_char, MNTOPT_DAX)) { + mp->m_flags |= XFS_MOUNT_DAX; +#endif } else { xfs_warn(mp, "unknown mount option [%s].", this_char); return -EINVAL; @@ -452,8 +458,8 @@ done: } struct proc_xfs_info { - int flag; - char *str; + uint64_t flag; + char *str; }; STATIC int @@ -474,6 +480,7 @@ xfs_showargs( { XFS_MOUNT_GRPID, "," MNTOPT_GRPID }, { XFS_MOUNT_DISCARD, "," MNTOPT_DISCARD }, { XFS_MOUNT_SMALL_INUMS, "," MNTOPT_32BITINODE }, + { XFS_MOUNT_DAX, "," MNTOPT_DAX }, { 0, NULL } }; static struct proc_xfs_info xfs_info_unset[] = { @@ -1501,6 +1508,20 @@ xfs_fs_fill_super( if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5) sb->s_flags |= MS_I_VERSION; + if (mp->m_flags & XFS_MOUNT_DAX) { + xfs_warn(mp, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + if (sb->s_blocksize != PAGE_SIZE) { + xfs_alert(mp, + "Filesystem block size invalid for DAX Turning DAX off."); + mp->m_flags &= ~XFS_MOUNT_DAX; + } else if (!sb->s_bdev->bd_disk->fops->direct_access) { + xfs_alert(mp, + "Block device does not support DAX Turning DAX off."); + mp->m_flags &= ~XFS_MOUNT_DAX; + } + } + error = xfs_mountfs(mp); if (error) goto out_filestream_unmount; -- 2.0.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from relay.sgi.com (relay1.corp.sgi.com [137.38.102.111]) by oss.sgi.com (Postfix) with ESMTP id DCE837F4E for ; Tue, 3 Mar 2015 17:31:18 -0600 (CST) Received: from cuda.sgi.com (cuda3.sgi.com [192.48.176.15]) by relay1.corp.sgi.com (Postfix) with ESMTP id CAC0B8F8066 for ; Tue, 3 Mar 2015 15:31:18 -0800 (PST) Received: from ipmail06.adl6.internode.on.net (ipmail06.adl6.internode.on.net [150.101.137.145]) by cuda.sgi.com with ESMTP id QFr6iiQ3KS7ufcEM for ; Tue, 03 Mar 2015 15:31:16 -0800 (PST) From: Dave Chinner Subject: [PATCH 6/6] xfs: add initial DAX support Date: Wed, 4 Mar 2015 10:30:27 +1100 Message-Id: <1425425427-16283-7-git-send-email-david@fromorbit.com> In-Reply-To: <1425425427-16283-1-git-send-email-david@fromorbit.com> References: <1425425427-16283-1-git-send-email-david@fromorbit.com> List-Id: XFS Filesystem from SGI List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: xfs-bounces@oss.sgi.com Sender: xfs-bounces@oss.sgi.com To: xfs@oss.sgi.com Cc: linux-fsdevel@vger.kernel.org, willy@linux.intel.com, jack@suse.cz From: Dave Chinner Add initial DAX support to XFS. To do this we need a new mount option to turn DAX on filesystem, and we need to propagate thi into the inode flags whenever an inode is instantiated so that the per-inode checks throughout the code Do The Right Thing. There are still some things remaining to be done: - needs per-inode flags to mark inodes as DAX enabled, and an inheritance flag to enable automatic filesystem propagation of the property - fails occasionally with zero length writes instead of ENOSPC errors, so error propagation inside/from the DAX code need work - occasionally creates two extents rather than a single larger extent like non-dax filesystems. - much more testing Signed-off-by: Dave Chinner --- fs/xfs/xfs_iops.c | 24 ++++++++++++------------ fs/xfs/xfs_mount.h | 2 ++ fs/xfs/xfs_super.c | 25 +++++++++++++++++++++++-- 3 files changed, 37 insertions(+), 14 deletions(-) diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 3ff24c3..887d196 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1195,22 +1195,22 @@ xfs_diflags_to_iflags( struct inode *inode, struct xfs_inode *ip) { - if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE) + uint16_t flags = ip->i_d.di_flags; + + inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC | + S_NOATIME | S_DAX); + + if (flags & XFS_DIFLAG_IMMUTABLE) inode->i_flags |= S_IMMUTABLE; - else - inode->i_flags &= ~S_IMMUTABLE; - if (ip->i_d.di_flags & XFS_DIFLAG_APPEND) + if (flags & XFS_DIFLAG_APPEND) inode->i_flags |= S_APPEND; - else - inode->i_flags &= ~S_APPEND; - if (ip->i_d.di_flags & XFS_DIFLAG_SYNC) + if (flags & XFS_DIFLAG_SYNC) inode->i_flags |= S_SYNC; - else - inode->i_flags &= ~S_SYNC; - if (ip->i_d.di_flags & XFS_DIFLAG_NOATIME) + if (flags & XFS_DIFLAG_NOATIME) inode->i_flags |= S_NOATIME; - else - inode->i_flags &= ~S_NOATIME; + /* XXX: Also needs an on-disk per inode flag! */ + if (ip->i_mount->m_flags & XFS_MOUNT_DAX) + inode->i_flags |= S_DAX; } /* diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 8c995a2..cd44e88 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -179,6 +179,8 @@ typedef struct xfs_mount { allocator */ #define XFS_MOUNT_NOATTR2 (1ULL << 25) /* disable use of attr2 format */ +#define XFS_MOUNT_DAX (1ULL << 62) /* TEST ONLY! */ + /* * Default minimum read and write sizes. diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 3ad0b17..0f26d7a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -112,6 +112,8 @@ static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */ #define MNTOPT_DISCARD "discard" /* Discard unused blocks */ #define MNTOPT_NODISCARD "nodiscard" /* Do not discard unused blocks */ +#define MNTOPT_DAX "dax" /* Enable direct access to bdev pages */ + /* * Table driven mount option parser. * @@ -363,6 +365,10 @@ xfs_parseargs( mp->m_flags |= XFS_MOUNT_DISCARD; } else if (!strcmp(this_char, MNTOPT_NODISCARD)) { mp->m_flags &= ~XFS_MOUNT_DISCARD; +#ifdef CONFIG_FS_DAX + } else if (!strcmp(this_char, MNTOPT_DAX)) { + mp->m_flags |= XFS_MOUNT_DAX; +#endif } else { xfs_warn(mp, "unknown mount option [%s].", this_char); return -EINVAL; @@ -452,8 +458,8 @@ done: } struct proc_xfs_info { - int flag; - char *str; + uint64_t flag; + char *str; }; STATIC int @@ -474,6 +480,7 @@ xfs_showargs( { XFS_MOUNT_GRPID, "," MNTOPT_GRPID }, { XFS_MOUNT_DISCARD, "," MNTOPT_DISCARD }, { XFS_MOUNT_SMALL_INUMS, "," MNTOPT_32BITINODE }, + { XFS_MOUNT_DAX, "," MNTOPT_DAX }, { 0, NULL } }; static struct proc_xfs_info xfs_info_unset[] = { @@ -1501,6 +1508,20 @@ xfs_fs_fill_super( if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5) sb->s_flags |= MS_I_VERSION; + if (mp->m_flags & XFS_MOUNT_DAX) { + xfs_warn(mp, + "DAX enabled. Warning: EXPERIMENTAL, use at your own risk"); + if (sb->s_blocksize != PAGE_SIZE) { + xfs_alert(mp, + "Filesystem block size invalid for DAX Turning DAX off."); + mp->m_flags &= ~XFS_MOUNT_DAX; + } else if (!sb->s_bdev->bd_disk->fops->direct_access) { + xfs_alert(mp, + "Block device does not support DAX Turning DAX off."); + mp->m_flags &= ~XFS_MOUNT_DAX; + } + } + error = xfs_mountfs(mp); if (error) goto out_filestream_unmount; -- 2.0.0 _______________________________________________ xfs mailing list xfs@oss.sgi.com http://oss.sgi.com/mailman/listinfo/xfs